merge-drafts
Intelligent draft merging tool with quality assessment and conflict resolution. Merges multiple drafts into a high-quality article, supporting multiple input formats, intelligent evaluation, conflict detection, highlight fusion, and multi-format output. Use when user says "合并稿子", "合稿", "merge drafts", "把这几篇合成一篇", "综合这几份稿子", "多稿合一", "稿件合并", "draft merge", "整合稿件", "汇总文稿", "把所有稿子合并", "起草稿合并", "初稿合并", "多个版本合并", "copy merge", "文章合并".
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/0xcjl/merge-draftsWhat This Skill Does
The merge-drafts skill is an advanced, AI-driven utility designed to synthesize multiple document sources into a single, cohesive, high-quality article. Unlike simple text concatenators, this skill employs a multi-step intelligent workflow that includes quality assessment, conflict detection, and logical fusion. It evaluates input documents based on five critical dimensions—structure, completeness, expression quality, unique insights, and thematic relevance—to identify the strongest 'base draft' and systematically integrate content from secondary sources.
By following strict writing guidelines, it ensures that your final output maintains a consistent tone, retains unique expressions, and manages terminology effectively across multiple versions. Whether you are dealing with technical documentation, case studies, or varied article versions, this tool ensures the output is professional, well-structured, and error-free.
Installation
To integrate this skill into your OpenClaw environment, execute the following command in your terminal:
clawhub install openclaw/skills/skills/0xcjl/merge-drafts
Use Cases
- Consolidating Research: Merge notes from different team members into a comprehensive report.
- Refining Multiple Drafts: Combine various iterations of a draft into a final version that preserves the best elements of each.
- Conflict Resolution: Automatically detect and flag contradictory data or viewpoints, ensuring that authoritative sources are prioritized.
- Content Standardization: Unify different writing styles or formats (docx, markdown, pdf, url) into a single, polished publication.
Example Prompts
- "把这几篇关于AI技术的稿子合成一篇,重点突出安全性分析,文件路径如下:/data/draft1.md, /data/draft2.md"
- "请汇总这几份稿件,把所有观点综合在一起,保持专业术语一致:[链接1], [链接2]"
- "我有三个版本的项目报告,帮我进行多稿合一,确保逻辑连贯且没有重复段落。"
Tips & Limitations
- Input Requirements: When providing Feishu documents, ensure they are set to 'anyone with the link can view' to avoid access errors.
- Prioritization: The tool naturally prioritizes content with explicit citations. If you have conflicting data, it is recommended to provide source links to ensure the AI selects the most accurate information.
- Refinement Boundaries: The skill is designed to avoid excessive re-writing; it performs 'minimal necessary editing' to correct grammar and syntax while preserving your unique voice.
- Quality Reports: Always check the included 'Merge Report' after execution to see how your drafts were evaluated and what changes were implemented.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-0xcjl-merge-drafts": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: file-read, file-write
Related Skills
autoresearch-pro
Automatically improve OpenClaw skills, prompts, or articles through iterative mutation-testing loops. Inspired by Karpathy's autoresearch. Use when user says 'optimize [skill]', 'autoresearch [skill]', 'improve my skill', 'optimize this prompt', 'improve my prompt', 'polish this article', 'improve this article', or explicitly requests quality improvement for any text-based content. Supports three modes: skill (SKILL.md files), prompt (any prompt text), and article (any document).
cjl-slides
Create stunning HTML presentations in 24 international design styles with strict design rules. Export to .pptx for PowerPoint editing. ## Design Philosophy - Aesthetic-first: each style is a curated visual system, not just colors - Font whitelist enforcement: prevents AI-generic typography - Container ratio lock (16:9): ensures consistent rendering across devices - Zero external dependencies: pure HTML/CSS/JS, works offline ## Usage 1. Activate → Select style by name/number or browse 24 options 2. Provide content (topic, audience, key points) or upload .pptx for conversion 3. Review generated HTML slides → request modifications (color/font/layout) 4. Optionally export .pptx for manual editing in PowerPoint ## Precautions - Fonts are restricted to a whitelist; custom fonts require adding to the allowed list first - Chart.js CDN is used; if blocked, falls back to jsdelivr mirror - HTML files must retain their relative structure when shared - .pptx export preserves exact colors and fonts but layout uses pptx-native elements ## Credits Design rules adapted from "专精 HTML 演示文稿的顶级视觉设计师" (24 design styles reference). Base HTML structure and tooling inspired by zarazhangrui/frontend-slides.
Diagram Drawing
Skill by 0xcjl
anti-sycophancy
Three-layer sycophancy defense based on ArXiv 2602.23971. Use /anti-sycophancy install to deploy all layers, or manage individually via install-claude-code / install-openclaw / uninstall / status / verify. Layer 1: CC-only hook; Layer 2: SKILL (cross-platform); Layer 3: CLAUDE.md (CC) / SOUL.md (OC).
auto-diary
Automatically write daily/weekly/monthly diary summaries and extract insights to auto-learn.md for HexaLoop.